Flow-based Time-aware Causal Structure Learning for Sequential Recommendation

Authors: Hangtong Xu, Yuanbo Xu, Huayuan Liu, En Wang

IJCAI 2025 | Venue PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We validate FCSRec on manifold real-world datasets, and experimental results show that FCSRec outperforms several state-of-the-art methods in recommendation performance. Our code is available at Code-link.
Researcher Affiliation Academia MIC Lab, College of Computer Science and Technology, Jilin University EMAIL, EMAIL
Pseudocode No The paper describes its methodology using mathematical formulations and natural language explanations (e.g., equations 1-16), but it does not include any clearly labeled pseudocode or algorithm blocks.
Open Source Code Yes Our code is available at Code-link. The proof of Theorem 1 can be found in in the code link . Due to the page limit, the appendix is available in our public code repository at https://github.com/MICLab-Rec/FCSRec.
Open Datasets Yes To comprehensively and fairly evaluate the models effectiveness, we conducted experiments using nine publicly available datasets encompassing a variety of recommendation scenarios (such as movies and pois) and different densities. We select five datasets of varying sizes ranging from 100k to 10M: Beauty, ML-100K, NYC, TKY, ML-1M, Gowalla and ML-10M to evaluate the robustness of the model to the dataset size.
Dataset Splits Yes Towards the data partition, we select each user s last previously un-interacted item as the target during the recommendation procedure and all the prior items for training.
Hardware Specification No The paper details software implementations and training configurations but does not provide specific hardware details (e.g., GPU models, CPU types) used for running the experiments.
Software Dependencies No We implement FCSRec and baselines in Py Torch. Our implementation of the baselines is based on the original papers or the open-source codebase Recbole [Zhao et al., 2021].
Experiment Setup Yes All models are trained with the Adam optimizer with early stopping at patience = 10. We set the learning rate to 1e-3 and the l2-regularization weight to 1e-6. For FCSRec, we tune the hyper-parameter concepts k in the range of [1, 8] for different datasets.